Research map / Detection and segmentation / CNN features
Unmixing Convolutional Features for Crisp Edge Detection
Linxi Huan, Nan Xue, Xianwei Zheng, Wei Ping He, Jianya Gong, Gui-Song Xia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add tracing loss and CoFusion (CATS) to RCF | RCF · BSDS500 (crispness-emphasized) | ODS: 0.585 -> 0.705 | Improved |
| add CATS to HED | HED · BSDS500 (crispness-emphasized) | ODS: 0.588 -> 0.666 | Improved |
| add CATS to BDCN | BDCN · BSDS500 (crispness-emphasized) | ODS: 0.636 -> 0.696 | Improved |
| add CATS to RCF | RCF · BSDS500 (standard evaluation) | ODS: 0.799 -> 0.805 | Improved |
| add CATS to RCF | RCF · NYUDv2 RGB (crispness-emphasized) | ODS: 0.398 -> 0.474 | Improved |
| add CATS to BDCN | BDCN · NYUDv2 RGB-HHA (standard evaluation) | ODS: 0.766 -> 0.770 | Improved |
| add CATS to RCF | RCF · Multicue Edge | ODS: 0.857 -> 0.892 | Improved |
| add CATS to RCF | RCF · Multicue Boundary | ODS: 0.817 -> 0.841 | Improved |
| add boundary tracing function alone to RCF (ablation) | RCF · NYUDv2 (crispness-emphasized) | ODS: 0.381 -> 0.382 | No clear effect |
| add texture suppression function alone to RCF (ablation) | RCF · NYUDv2 (crispness-emphasized) | ODS: 0.381 -> 0.383 | No clear effect |
| combine boundary tracing and texture suppression (tracing loss) (ablation) | RCF · NYUDv2 (crispness-emphasized) | ODS: 0.381 -> 0.411 | Improved |
| add CoFusion block alone to RCF with cross entropy (ablation) | RCF · NYUDv2 (crispness-emphasized) | ODS: 0.381 -> 0.381 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BDCN — BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection (TPAMI 2020) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Deep Crisp Boundaries (CVPR 2017 · similarity 0.88)
- Learning to Predict Crisp Boundaries (ECCV 2018 · similarity 0.87)
- Richer Convolutional Features for Edge Detection (CVPR 2017 · similarity 0.86)
- MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision (CVPR 2026 · similarity 0.85)
- DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection (AAAI 2024 · similarity 0.85)
- Harnessing Edge Information for Improved Robustness in Vision Transformers (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
